Year: 2017
Type: conference-paper
Abstract: We propose an end-to-end deep learning architecture for word-level visual speech recognition. The system is a combination of spatiotemporal convolutional, residual and bidirectional Long Short-Term Memory networks. We train and evaluate it on the Lipreading In-The-Wild benchmark, a challenging database of 500-size target-words consisting of 1.28sec video excerpts from BBC TV broadcasts. The proposed network attains word accuracy equal to 83.0, yielding 6.8 absolute improvement over the current state-of-the-art, without using information about word boundaries during training or testing.
Source: Interspeech (USB)
Authors: Themos Stafylakis, Georgios Tzimiropoulos
Institution: University of Nottingham
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: European Commission
OpenAlex ID: W2596627958